Open-source alternatives to Mjolnir

Kit is a desktop automation framework and scriptable UI toolkit designed for building personalized productivity tools. It serves as a cross-platform CLI wrapper and macOS system automator, providing an environment to execute scripts that manage operating system tasks, file management, and application workflows. The project distinguishes itself with a dedicated LLM integration layer for structured data extraction and text generation, alongside a specialized UI framework for creating interactive input forms, HTML windows, and floating widgets. It features deep macOS integration through AppleScr

This project is a desktop automation scripting framework and shell script command runner. It allows users to execute custom scripts and workflows from a central launcher to automate repetitive desktop tasks and system operations. The framework functions as a unified command interface and a JSON input automation bridge, serializing search queries into arguments passed to the execution environment. It integrates large language model prompts directly into the desktop interface to automate content generation and answer questions. The system handles a broad range of capabilities including the exe

Free RPA tool by AI Singapore

Greenshot is a Windows screen capture tool and productivity suite designed to capture screen regions, specific windows, or full displays as image files. It functions as an image annotation editor and external image uploader, allowing users to process visual assets before saving or sharing them. The project emphasizes automated workflows through the use of global hotkeys and command-line routing to send captured files to external applications. It supports high-resolution displays with specific scaling for high DPI screens to ensure visual consistency. The software provides capabilities for im

Phoenix is a macOS workspace automator and window manager that uses a JavaScript scripting engine to control system-level behaviors. It functions as an AppleScript automation bridge, allowing users to programmatically manipulate application states, window geometry, and desktop interactions. The project enables the creation of custom workflows by binding keyboard shortcuts to JavaScript functions. This allows for the automation of complex system actions, such as organizing application layouts across multiple screens and managing virtual spaces. Its capability surface covers window and applica

KeymouseGo is an input automation tool and macro recorder designed to capture, edit, and replay keyboard and mouse sequences to automate repetitive desktop tasks. It functions as a scriptable input automator that translates recorded user interactions into reusable blueprints for automated playback. The system distinguishes itself through a logic-based scripting framework that supports conditional branching, sub-routine calls, and jump-to-labels for complex workflow control. It further extends runtime behavior via a plugin system that allows for the registration of custom functions to modify t

uPic is a native macOS application designed for uploading images and files to cloud hosting services and private backends. It functions as a cloud image hosting tool and a custom API upload client that generates formatted links for shared content. The project distinguishes itself by allowing users to configure private backend endpoints with specific HTTP methods, headers, and server URLs. It converts uploaded file addresses into Markdown or HTML snippets, which are then written back to the system clipboard via customizable URL templates. The application integrates with macOS system framework

RPA-Python is a robotic process automation framework for automating repetitive tasks across web browsers, desktop applications, and operating systems using Python scripts. It functions as a desktop process automator and browser automation tool designed to reduce manual labor and human error in digital workflows. The project includes an OCR screen data extractor for capturing snapshots and extracting text from images via optical character recognition. It also provides a system command wrapper for executing shell commands and managing local file operations, such as downloading files from URLs a

Hammerspoon is a programmable automation engine for macOS that enables deep system-level control through a Lua scripting environment. By bridging high-level scripts with native Objective-C APIs, it allows users to interact with the operating system's accessibility tree, intercept hardware input streams, and manage the lifecycle of running applications. The project distinguishes itself through an event-driven architecture that registers asynchronous hooks for system notifications and hardware events. This allows for real-time automation, such as remapping keyboard and mouse inputs, managing wi

This application is a cross-platform desktop utility designed for automated translation, optical character recognition, and speech synthesis. It functions as a modular client that integrates various local and remote language services, allowing users to process text through hotkeys, clipboard monitoring, or direct input. The software distinguishes itself through a plugin-based architecture and a built-in automation framework. By exposing a local network interface, it enables external applications and scripts to programmatically trigger its translation and recognition workflows. Users can furth

This project is an autonomous desktop automation agent that interprets natural language instructions to control applications, browser interfaces, and system terminals. It functions as a cross-platform utility designed to manage complex workflows by integrating visual screen analysis with system-level input simulation. The agent distinguishes itself through its ability to perform tasks asynchronously, ensuring that web and terminal operations run in the background without interrupting the active user session or desktop focus. By combining computer vision to map interface elements with event-dr

This is a collection of Python automation scripts and utility tools designed to handle repetitive technical tasks, system administration, and developer workflows. The project serves as a suite for task automation, data utility, and web automation. The collection includes specialized tools for multimedia processing, such as optical character recognition for extracting text from images, speech-to-text conversion, and real-time face and human body detection. It also features web scraping and monitoring capabilities to track product prices, fetch external API content, and automate interactions wi

Agent-S is a multimodal AI agent and LLM desktop automation framework designed to control operating systems through graphical user interface interactions. It functions as a computer use interface, utilizing vision-language grounding to translate natural language goals into precise screen coordinates and system actions. The project differentiates itself by combining structured accessibility tree inspection with vision-based element localization. It manages cross-application workflows by mapping conceptual descriptions to physical pixels and simulating low-level keyboard and mouse events to mov

Bytebot is an LLM desktop automation framework and virtual Linux desktop environment. It enables AI agents to plan and execute mouse and keyboard actions on a virtual computer using natural language, allowing for autonomous desktop automation and the integration of legacy systems that lack native APIs. The system operates as an LLM API gateway and a Model Context Protocol server, routing requests across multiple language model providers with integrated load balancing and rate limiting. It provides isolated, containerized environments where agents use visual reasoning to interpret screenshots

TechXueXi is an automated learning tool designed to complete daily tasks and quizzes on a political education platform, earning points without manual intervention. It combines headless browser automation with human-like behavior simulation, randomizing user-agent strings and mimicking interaction patterns to avoid detection during automated sessions. The tool is built as a Python script that can run directly from source code after installing dependencies and a browser driver, or be deployed inside a Docker container for persistent, 24/7 operation on servers, VPS, or NAS devices. It supports c

Taskwarrior is a command-line task manager that lets you create, modify, filter, and complete to-do items directly from the terminal. It stores all tasks in a single plain-text file for portability and manual editing, and includes a custom expression language for selecting tasks by status, priority, tags, and date ranges. The tool distinguishes itself through several integrated capabilities. It computes a numeric urgency score for each task based on weighted factors like age, tags, and due date to determine ordering. A recurrence template engine generates new task instances from a template af

Komodo is a remote server orchestrator and container deployment platform. It provides a centralized interface for managing multiple remote hosts through lightweight agents, coordinating Docker Swarm and Kubernetes clusters, and automating software delivery via integrated CI/CD pipelines. The system distinguishes itself with a TypeScript-based automation engine that executes typed scripts against the system API for complex operational workflows. It supports infrastructure-as-code through TOML-based declarative configuration synchronization and provides ephemeral build infrastructure that provi

Trilium is a hierarchical personal knowledge base and digital garden tool designed to organize information into a tree of linked nodes. It functions as a JavaScript programmable wiki and a self-hosted note server, allowing users to maintain a private database of documents synchronized across multiple devices. The platform distinguishes itself through an embedded scripting engine for automating tasks and a REST API that exposes internal data and actions to external tools. Users can further extend the system by modifying the user interface layout and styling through a custom theme engine. The

Babashka is a native Clojure scripting interpreter and shell scripting language designed for system automation and command-line tasks. It functions as a compiled binary that executes Clojure code directly, eliminating the startup overhead associated with a Java Virtual Machine. The runtime is an extensible Clojure environment that supports a pod extension system, allowing external binaries to be loaded as libraries to add new functionality to the execution environment. Its capability surface includes support for building extensible command-line tools and deploying Clojure scripts as serverle

Openwork is an AI agent for desktop automation that uses large language models to execute browser tasks, manage local files, and automate desktop workflows. It operates on a local-first execution model, translating natural language prompts into sequences of tool calls to perform digital chores. The system functions as a framework for defining and saving repeatable sequences of actions as reusable skills. It integrates large language models with third-party services and local APIs to synchronize data and share files. The agent includes capabilities for headless browser automation to conduct r

This project is a collection of bash automation scripts and command-line utilities designed to automate common tasks and retrieve information from web APIs. It serves as a toolkit for developer references, network diagnostics, and media access directly from the terminal. A central component of the suite is a GitHub Gist manager that handles the full lifecycle of code snippets. This includes cloning and syncing Gists into local directories for offline access, organizing content through hashtags, and searching through snippet descriptions and file contents using regular expressions. The toolki

Elvish is a shell that combines interactive command-line use with a structured scripting language, designed to make both everyday terminal work and automation tasks more predictable and readable. It parses, compiles, and executes code in three phases, catching syntax and variable errors before any code runs, and it aborts execution on command failure by default to prevent silent errors. The shell introduces value-oriented pipelines that pass structured data like lists, maps, and closures between commands, preserving types without serialization. It also mixes traditional byte streams with thes

jdpro is a dockerized automation bot and scheduled task runner designed to automate reward collection and the conversion of expiring digital assets. It operates as a set of scripts deployed via containers to ensure consistent installation and execution across different hosts. The project includes a specialized authentication system that transforms raw keys and manages session cookies through environment variables to maintain automated login states. It also features a webhook notification manager that routes task updates to external services, utilizing keyword-based filtering and payload split

This repository provides a collection of interactive sample applications and reference implementations for the Electron framework. It serves as a library of API reference demos designed to help developers learn how to implement core desktop features. The project features visual demonstrations of cross-platform GUI management and practical examples of native operating system integration. It includes dedicated samples for handling native modules, crash reports, and the configuration of security implementations such as content security policies and process sandboxing. The codebase covers a broa

This project is a library of automation scripts designed for the BoxJs environment. It functions as an external API client and integration interface for interacting with remote servers. The system provides a persistent local data store to maintain state between script executions by saving and retrieving strings and JSON objects. It enables data exchange through structured JSON objects and supports both synchronous and asynchronous network requests using custom headers.

Open-computer-use is a framework designed to connect vision-capable language models to isolated cloud-based desktop environments. It functions as an agentic interface that enables autonomous systems to interact with graphical user interfaces by simulating mouse movements, keyboard keystrokes, and shell commands. By bridging language models with remote workspaces, the platform facilitates the execution of complex, long-running tasks within secure, sandboxed environments. The platform distinguishes itself through its ability to orchestrate thousands of concurrent, isolated instances, making it

UI-TARS-desktop is a cross-platform desktop application designed to automate software interface interactions. It functions as a local agent environment that interprets graphical user interfaces through multimodal visual-language model reasoning, allowing it to navigate and manipulate software by simulating human-like mouse and keyboard inputs. The platform distinguishes itself by executing all visual recognition and decision-making logic directly on the host machine. This local inference model ensures that screen data and sensitive information remain private, as no processing is offloaded to